lakehouse/scripts/distillation/distill.ts

// distill.ts — single-entry CLI dispatcher for the distillation
// pipeline. Mirrors the spec's `./scripts/distill <command>` shape.
//
// USAGE
//   bun run scripts/distillation/distill.ts <command> [flags]
//
// COMMANDS
//   build-evidence     materialize EvidenceRecord rows from data/_kb/*.jsonl
//   score              run deterministic Success Scorer
//   export-rag         RAG export (--include-review opt-in)
//   export-sft         SFT export (--include-partial opt-in)
//   export-preference  preference export
//   export-all         RAG + SFT + preference (no opt-ins by default)
//   health             evidence health audit
//
// All commands accept --dry-run.

import { materializeAll } from "./build_evidence_index";
import { scoreAll } from "./score_runs";
import { exportRag } from "./export_rag";
import { exportSft } from "./export_sft";
import { exportPreference } from "./export_preference";
import { runAllWithReceipts } from "./receipts";
import { replay } from "./replay";
import { TRANSFORMS } from "./transforms";
import { spawnSync } from "node:child_process";

const DEFAULT_ROOT = process.env.LH_DISTILL_ROOT ?? "/home/profit/lakehouse";

async function main() {
  const cmd = process.argv[2];
  const dry_run = process.argv.includes("--dry-run");
  const include_partial = process.argv.includes("--include-partial");
  const include_review = process.argv.includes("--include-review");
  const recorded_at = new Date().toISOString();

  switch (cmd) {
    case "build-evidence": {
      const r = await materializeAll({ root: DEFAULT_ROOT, transforms: TRANSFORMS, recorded_at, dry_run });
      console.log(`[build-evidence] in=${r.totals.rows_read} out=${r.totals.rows_written} skip=${r.totals.rows_skipped} dedup=${r.totals.rows_deduped}`);
      if (!dry_run) console.log(`[build-evidence] receipt: ${r.receipt_path}`);
      if (!r.receipt.validation_pass) process.exit(1);
      break;
    }
    case "score": {
      const r = await scoreAll({ root: DEFAULT_ROOT, recorded_at, dry_run });
      const c = r.totals.by_category;
      console.log(`[score] in=${r.totals.rows_read} out=${r.totals.rows_written} acc=${c.accepted ?? 0} part=${c.partially_accepted ?? 0} rej=${c.rejected ?? 0} hum=${c.needs_human_review ?? 0}`);
      if (!dry_run) console.log(`[score] receipt: ${r.receipt_path}`);
      break;
    }
    case "export-rag": {
      const r = await exportRag({ root: DEFAULT_ROOT, recorded_at, include_review, dry_run });
      console.log(`[export-rag] in=${r.records_read} out=${r.records_exported} ${r.quarantine_summary}`);
      console.log(`[export-rag] output: ${r.output_path}${include_review ? " (review included)" : ""}`);
      break;
    }
    case "export-sft": {
      const r = await exportSft({ root: DEFAULT_ROOT, recorded_at, include_partial, dry_run });
      console.log(`[export-sft] in=${r.records_read} out=${r.records_exported} ${r.quarantine_summary}`);
      console.log(`[export-sft] output: ${r.output_path}${include_partial ? " (partial included)" : ""}`);
      break;
    }
    case "export-preference": {
      const r = await exportPreference({ root: DEFAULT_ROOT, recorded_at, dry_run });
      console.log(`[export-preference] in=${r.records_read} pairs=${r.pairs_exported} task_ids_paired=${r.task_ids_with_pairs} ${r.quarantine_summary}`);
      console.log(`[export-preference] output: ${r.output_path}`);
      break;
    }
    case "export-all": {
      const rRag = await exportRag({ root: DEFAULT_ROOT, recorded_at, include_review, dry_run });
      const rSft = await exportSft({ root: DEFAULT_ROOT, recorded_at, include_partial, dry_run });
      const rPref = await exportPreference({ root: DEFAULT_ROOT, recorded_at, dry_run });
      console.log("");
      console.log("─── export-all summary ───");
      console.log(`  RAG:        in=${rRag.records_read} out=${rRag.records_exported} ${rRag.quarantine_summary}`);
      console.log(`  SFT:        in=${rSft.records_read} out=${rSft.records_exported} ${rSft.quarantine_summary}`);
      console.log(`  Preference: in=${rPref.records_read} pairs=${rPref.pairs_exported} ${rPref.quarantine_summary}`);
      break;
    }
    case "run-all": {
      // Phase 5 entry — full pipeline with structured receipts.
      const r = await runAllWithReceipts({ root: DEFAULT_ROOT, include_partial, include_review });
      console.log(`[run-all] run_id=${r.run_id} overall_passed=${r.summary.overall_passed}`);
      console.log(`[run-all] datasets: rag=${r.summary.rag_records} sft=${r.summary.sft_records} pref=${r.summary.preference_pairs}`);
      console.log(`[run-all] drift severity=${r.drift.severity}`);
      console.log(`[run-all] reports/distillation/${r.run_id}/summary.md`);
      if (!r.summary.overall_passed) process.exit(1);
      break;
    }
    case "replay": {
      const taskIdx = process.argv.indexOf("--task");
      if (taskIdx < 0 || !process.argv[taskIdx + 1]) {
        console.error("usage: distill.ts replay --task \"<input>\" [--local-only] [--allow-escalation] [--no-retrieval]");
        process.exit(2);
      }
      const r = await replay({
        task: process.argv[taskIdx + 1],
        local_only: process.argv.includes("--local-only"),
        allow_escalation: process.argv.includes("--allow-escalation"),
        no_retrieval: process.argv.includes("--no-retrieval"),
      }, DEFAULT_ROOT);
      console.log(`[replay] run_id=${r.recorded_run_id}`);
      console.log(`[replay] retrieval: ${r.context_bundle ? r.context_bundle.retrieved_playbooks.length + " playbooks" : "DISABLED"}`);
      console.log(`[replay] escalation_path: ${r.escalation_path.join(" → ")}`);
      console.log(`[replay] model_used: ${r.model_used} · ${r.duration_ms}ms`);
      console.log(`[replay] validation: ${r.validation_result.passed ? "PASS" : "FAIL"}${r.validation_result.reasons.length ? " (" + r.validation_result.reasons.join("; ") + ")" : ""}`);
      console.log("");
      console.log("─── response ───");
      console.log(r.model_response.slice(0, 1500));
      if (r.model_response.length > 1500) console.log(`... [${r.model_response.length - 1500} more chars]`);
      if (!r.validation_result.passed && !process.argv.includes("--allow-escalation")) process.exit(1);
      break;
    }
    case "acceptance": {
      // Phase 6 — fixture-driven end-to-end gate. Spawns the dedicated
      // acceptance script so its non-zero exit propagates.
      const r = spawnSync("bun", ["run", "scripts/distillation/acceptance.ts"], {
        cwd: DEFAULT_ROOT, stdio: "inherit",
      });
      process.exit(r.status ?? 1);
    }
    case "receipts": {
      // Read receipts for a previously-run pipeline.
      const idx = process.argv.indexOf("--run-id");
      if (idx < 0 || !process.argv[idx + 1]) {
        console.error("usage: distill.ts receipts --run-id <id>");
        process.exit(2);
      }
      const run_id = process.argv[idx + 1];
      const path = `${DEFAULT_ROOT}/reports/distillation/${run_id}/summary.md`;
      // Defer to bun's file APIs to keep this lean.
      const { readFileSync } = await import("node:fs");
      try { console.log(readFileSync(path, "utf8")); }
      catch { console.error(`run not found: ${path}`); process.exit(2); }
      break;
    }
    case "health":
    case "help":
    case undefined: {
      console.log("Usage: bun run scripts/distillation/distill.ts <command> [flags]");
      console.log("");
      console.log("Commands:");
      console.log("  build-evidence     materialize EvidenceRecord rows");
      console.log("  score              run deterministic Success Scorer");
      console.log("  export-rag         RAG export (--include-review opt-in)");
      console.log("  export-sft         SFT export (--include-partial opt-in)");
      console.log("  export-preference  preference export");
      console.log("  export-all         RAG + SFT + preference");
      console.log("  run-all            full pipeline with structured receipts (Phase 5)");
      console.log("  receipts           read summary for a run (--run-id <id>)");
      console.log("  acceptance         fixture-driven end-to-end gate (Phase 6)");
      console.log("  replay             retrieval-driven local-model bootstrap (Phase 7) — needs --task");
      console.log("");
      console.log("Flags: --dry-run, --include-partial, --include-review,");
      console.log("       --task \"<text>\", --local-only, --allow-escalation, --no-retrieval");
      break;
    }
    default:
      console.error(`unknown command: ${cmd}. Try 'help'.`);
      process.exit(2);
  }
}

main().catch(e => { console.error(e); process.exit(1); });